rag-chunking-strategy
Document chunking with multiple strategies including semantic, recursive, and fixed-size chunking
Best use case
rag-chunking-strategy is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Document chunking with multiple strategies including semantic, recursive, and fixed-size chunking
Teams using rag-chunking-strategy should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/rag-chunking-strategy/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How rag-chunking-strategy Compares
| Feature / Agent | rag-chunking-strategy | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Document chunking with multiple strategies including semantic, recursive, and fixed-size chunking
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# RAG Chunking Strategy Skill ## Capabilities - Implement multiple document chunking strategies - Configure semantic chunking based on content boundaries - Set up recursive character text splitting - Design fixed-size chunking with overlap - Implement document-aware chunking (markdown, code, etc.) - Optimize chunk sizes for retrieval quality ## Target Processes - rag-pipeline-implementation - chunking-strategy-design ## Implementation Details ### Chunking Strategies 1. **RecursiveCharacterTextSplitter**: Hierarchical splitting with separators 2. **SemanticChunker**: Embedding-based semantic boundaries 3. **TokenTextSplitter**: Token-aware splitting 4. **MarkdownHeaderTextSplitter**: Structure-aware markdown splitting 5. **CodeSplitter**: Language-aware code chunking ### Configuration Options - Chunk size (characters or tokens) - Chunk overlap percentage - Separator hierarchy - Embedding model for semantic chunking - Document type detection ### Best Practices - Match chunk size to embedding model limits - Use appropriate overlap for context preservation - Test retrieval quality with different strategies - Consider document structure in strategy selection ### Dependencies - langchain-text-splitters - sentence-transformers (for semantic chunking)
Related Skills
GTM Strategy
Go-to-market planning and execution capabilities for product launches
digital-engagement-strategy
Develop digital content strategies including virtual exhibitions, online programming, social media campaigns, and digital collection access
control-strategy-designer
Process control strategy design skill for control structure selection, loop configuration, and regulatory control
category-strategy-builder
Category management strategy development using Kraljic Matrix and portfolio optimization
fx-hedging-strategy-modeler
Foreign exchange exposure analysis and hedging strategy skill with hedge effectiveness testing
blue-ocean-strategy
Value innovation and market space creation analysis using Blue Ocean frameworks
strategy-stress-testing-skill
Strategy robustness testing, scenario-based evaluation, vulnerability identification, and adaptation planning
Incremental Model Strategy Selector
Selects and configures optimal incremental model strategies
process-builder
Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.
babysitter
Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)
yolo
Run Babysitter autonomously with minimal manual interruption.
user-install
Install the user-level Babysitter Codex setup.